{"url":"/method/pnas","slug":"pnas","name":"PNAS","full_name":"Progressive Neural Architecture Search","full_name_withheld":false,"description_markdown":"**Progressive Neural Architecture Search**, or **PNAS**, is a method for learning the structure of convolutional neural networks (CNNs). It uses a sequential model-based optimization (SMBO) strategy, where we search the space of cell structures, starting with simple (shallow) models and progressing to complex ones, pruning out unpromising structures as we go. \r\n\r\nAt iteration $b$ of the algorithm, we have a set of $K$ candidate cells (each of size $b$ blocks), which we train and evaluate on a dataset of interest. Since this process is expensive, PNAS also learns a model or surrogate function which can predict the performance of a structure without needing to train it. We then expand the $K$ candidates of size $b$ into $K' \\gg K$ children, each of size $b+1$. The surrogate function is used to rank all of the $K'$ children, pick the top $K$, and then train and evaluate them. We continue in this way until $b=B$, which is the maximum number of blocks we want to use in a cell.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Progressive Neural Architecture Search","paper":"/paper/progressive-neural-architecture-search","first_author":"Chenxi Liu","n_authors":10,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/progressive-neural-architecture-search"},"source":{"url":"http://arxiv.org/abs/1712.00559v3","title":"Progressive Neural Architecture Search","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Neural Architecture Search","url":"/methods/category/neural-architecture-search","pwc_aliases":[]}],"n_papers_tagged":16,"archive_num_papers":16,"papers_newest_first":[{"paper":"/paper/barrier-free-microhabitats-self-organized","title":"Barrier-Free Microhabitats: Self-Organized Seclusion in Microbial Communities","date":"2025-03-27","arxiv_id":"2503.21621","n_code_links":1,"syntology":null},{"paper":null,"title":"Mixed Delay/Nondelay Embeddings Based Neuromorphic Computing with Patterned Nanomagnet Arrays","date":"2024-12-05","arxiv_id":"2412.04622","n_code_links":0,"syntology":null},{"paper":null,"title":"Fluctuations and the limit of predictability in protein evolution","date":"2024-12-02","arxiv_id":"2412.01969","n_code_links":0,"syntology":null},{"paper":null,"title":"From Complexity to Clarity: How AI Enhances Perceptions of Scientists and the Public's Understanding of Science","date":"2024-04-23","arxiv_id":"2405.00706","n_code_links":0,"syntology":null},{"paper":null,"title":"Cell motility modes are selected by the interplay of mechanosensitive adhesion and membrane tension","date":"2023-05-31","arxiv_id":"2306.00236","n_code_links":0,"syntology":null},{"paper":null,"title":"Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problems","date":"2022-10-08","arxiv_id":"2210.04118","n_code_links":0,"syntology":null},{"paper":null,"title":"POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique","date":"2022-10-06","arxiv_id":"2210.02959","n_code_links":0,"syntology":null},{"paper":null,"title":"Stochastic Gradient Descent and Anomaly of Variance-flatness Relation in Artificial Neural Networks","date":"2022-07-11","arxiv_id":"2207.04932","n_code_links":0,"syntology":null},{"paper":null,"title":"Information Cocoons in Online Navigation","date":"2021-09-14","arxiv_id":"2109.06589","n_code_links":0,"syntology":null},{"paper":null,"title":"Learning Interaction Kernels for Agent Systems on Riemannian Manifolds","date":"2021-01-30","arxiv_id":"2102.00327","n_code_links":0,"syntology":null},{"paper":null,"title":"Stabilizing Deep Tomographic Reconstruction","date":"2020-08-04","arxiv_id":"2008.01846","n_code_links":0,"syntology":null},{"paper":null,"title":"On the Transcriptomic Signature and General Stress State Associated with Aneuploidy","date":"2020-07-28","arxiv_id":"2007.14585","n_code_links":0,"syntology":null},{"paper":"/paper/weak-sindy-for-partial-differential-equations","title":"Weak SINDy For Partial Differential Equations","date":"2020-07-06","arxiv_id":"2007.02848","n_code_links":2,"syntology":null},{"paper":null,"title":"Sparse Identification of Nonlinear Dynamical Systems via Reweighted $\\ell_1$-regularized Least Squares","date":"2020-05-27","arxiv_id":"2005.13232","n_code_links":0,"syntology":null},{"paper":"/paper/auto-keras-efficient-neural-architecture","title":"Auto-Keras: An Efficient Neural Architecture Search System","date":"2018-06-27","arxiv_id":"1806.10282","n_code_links":13,"syntology":{"ran":3,"of":6,"unverified":3,"pointer_only":0}},{"paper":"/paper/progressive-neural-architecture-search","title":"Progressive Neural Architecture Search","date":"2017-12-02","arxiv_id":"1712.00559","n_code_links":18,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":2}}],"papers_shown":16,"tasks":[{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":3},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/articles","name":"Articles","papers":1},{"task":"/task/automl","name":"AutoML","papers":1},{"task":"/task/bayesian-optimization","name":"Bayesian Optimization","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/computed-tomography-ct","name":"Computed Tomography (CT)","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/evolutionary-algorithms","name":"Evolutionary Algorithms","papers":1},{"task":"/task/friction","name":"Friction","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":1},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":1},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":1},{"task":null,"name":"Relation","papers":1}],"tasks_shown":20,"n_tasks":24,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":1},{"year":"2020","papers":4},{"year":"2021","papers":2},{"year":"2022","papers":3},{"year":"2023","papers":1},{"year":"2024","papers":3},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/pnas"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}